Methods and Apparatus to Characterize Households with Media Meter Data

1. A method to calculate a probability of a first media device having a first power status, comprising: identifying, with a processor, a power status and a first automatic gain control (AGC) value for an exposure minute from a panelist audience meter in a first household, the panelist audience meter including a power sensor to sense a power status of a second media device in the first household; identifying, with the processor a second AGC value of a first media meter (MM) during a household tuning minute in the first household, the first MM including a microphone to collect audio data; and preventing erroneous crediting by: calculating, with the processor, model coefficients based on the exposure minute and the household tuning minute; calculating, with the processor, a power status probability for the first media device in a second household based on the model coefficients and data from a second MM in the second household, the second household not including a panelist audience meter having a power sensor; and determining whether to credit a media exposure identified by the second MM in the second household based on the power status probability.

2. A method as defined in claim 1 , wherein the data from the second MM includes daypart information and AGC values from the second MM in the second household.

3. A method as defined in claim 1 , wherein the calculating of the model coefficients further includes calculating the model coefficients with an independent variable based on a number of minutes since the first MM in the first household credited a station.

4. A method as defined in claim 1 , further including identifying a number of minutes associated with the first media device in the second household and containing neither codes nor signatures having a match with a reference database.

5. A method as defined in claim 4 , wherein the calculating of the power status probability determines whether the number of minutes associated with the first media device in the second household is associated with an OFF power state or an all other tuning state.

6. A method as defined in claim 4 , wherein the calculating of the power status probability determines whether the number of minutes associated with the first media device in the second household is associated with a muted state.

7. A method as defined in claim 4 , further including attributing the number of minutes containing neither codes nor signatures to video game usage.

8. A method as defined in claim 1 , further including determining daypart information associated with the household tuning minute.

9. An apparatus to calculate a probability of a first media device being in a first power state, comprising: an automatic gain control (AGC) monitor to identify a first AGC value of a panelist audience meter during an exposure minute in a first household, the panelist audience meter including a power sensor to sense a power status of a second media device in the first household, the AGC monitor to identify a second AGC value of a first media meter (MM) during a household tuning minute in the first household, the first MM including a microphone to collect audio data; and a modeling engine to prevent erroneous crediting by: calculating model coefficients based on the exposure minute and the household tuning minute; calculating a power status probability for the first media device in a second household based on the model coefficients and data from a second MM in the second household, the second household not including a the panelist audience meter having a power sensor; and determining whether to credit a media exposure identified by the second MM in the second household based on the power status probability.

10. An apparatus as defined in claim 9 , wherein the data from the second MM includes daypart information and AGC values.

11. An apparatus as defined in claim 9 , wherein the modeling engine is to calculate the model coefficients with an independent variable based on a number of minutes since the first MM in the first household credited a station.

12. An apparatus as defined in claim 9 , further including a detection engine to identify a number of minutes associated with the first media device in the second household and containing neither codes nor signatures having a match with a reference database.

13. An apparatus as defined in claim 12 , wherein the modeling engine is to determine whether the number of minutes associated with the first media device in the second household is associated with an OFF power state or an all other tuning (AOT) state based on the power status probability calculation.

14. An apparatus as defined in claim 12 , wherein the modeling engine is to determine whether the number of minutes associated with the first media device in the second household containing neither codes nor signatures is associated with a muted state.

15. An apparatus as defined in claim 12 , wherein the modeling engine is to attribute the number of minutes containing neither codes nor signatures to video game usage.

16. An apparatus as defined in claim 9 , wherein the AGC monitor is to identify daypart information associated with the household tuning minute.

17. A tangible machine readable storage medium comprising instructions that, when executed, cause a machine to at least: identify a power status and a first automatic gain control (AGC) value for an exposure minute from a panelist audience meter in a first household, the panelist audience meter including a power sensor to sense a power status of a first media device in the first household; identify a second AGC value of a first media meter (MM) during a household tuning minute in the first household, the first MM including a microphone to collect audio data; and prevent erroneous crediting by: calculating model coefficients based on the exposure minute and the household tuning minute; calculating a power status probability for a second media device in a second household based on the model coefficients and data from a second MM in the second household, the second household not including a panelist audience meter having a power sensor; and determining whether to credit a media exposure identified by the second MM in the second household based on the power status probability.

18. A storage medium as defined in claim 17 , wherein the instructions, when executed, further cause the data from the second MM to include daypart information and AGC values.

19. A storage medium as defined in claim 17 , wherein the instructions, when executed, cause the machine to calculate the model coefficients with an independent variable based on a number of minutes since the first MM in the first household credited a station.

20. A storage medium as defined in claim 17 , wherein the instructions, when executed, further cause the machine to identify a number of minutes associated with the second media device in the second household and containing neither codes nor signatures having a match with a reference database.

21. A storage medium as defined in claim 20 , wherein the instructions, when executed, further cause the machine to determine whether the number of minutes associated with the second media device in the second household is associated with an OFF power state or an all other tuning state based on the power status probability calculation.

22. A storage medium as defined in claim 20 , wherein the instructions, when executed, further cause the machine to determine whether the number of minutes associated with the second media device in the second household containing neither codes nor signatures is associated with a muted state.

23. A storage medium as defined in claim 17 , wherein the instructions, when executed, further cause the machine to determine daypart information associated with the household tuning minute.